© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 18214
    Prev
    Next
    INDEX
    Explanations

    sequences involving accidents and injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LocalizedString
    -0.07
    burgh
    -0.07
    Ñĥки
    -0.07
    xFFF
    -0.07
    CEE
    -0.07
    ãĥ¼ãĥģ
    -0.07
     Pier
    -0.07
    acher
    -0.07
    umd
    -0.07
    FFE
    -0.07
    POSITIVE LOGITS
    /respond
    0.06
    15
    0.06
    467
    0.06
    Ãłng
    0.06
     norms
    0.05
    uj
    0.05
    .Args
    0.05
    ka
    0.05
     CM
    0.05
    æŃ£
    0.05
    Activations Density 0.003%

    No Known Activations